I will show you how to install LiteLLM using the Helm chart in this article.
Step 1: Set Up Helm
Ensure that Helm is installed on your local machine. If you haven’t done so, refer to the installation instructions on the official Helm website.
Step 2: Add the Helm Repository
Add the GitHub repository with the LiteLLM Helm charts to your Helm repositories:
helm repo add litellm https://chetankapoor.github.io/litellm-helm-charts
Step 3: Update Your Helm Repositories
After adding the repository, update your local Helm chart repository cache:
helm repo update
Step 4: Install LiteLLM using Helm
The following command will install LiteLLM for you. Depending on your needs, you can customize the namespace and release name:
helm install litellm litellm/litellm --namespace <your-namespace> --create-namespace
Optional: Custom Values
Create values.yaml file with your desired configurations if you need to customize the installation (e.g., setting environment variables, and resource limits). During installation, you can use this file:
# values.yaml
replicaCount: 1
image:
repository: ghcr.io/berriai/litellm
tag: main
service:
type: LoadBalancer
port: 8000
Then run the install command with your custom values:
helm install litellm litellm/litellm --namespace <your-namespace> --create-namespace -f values.yaml
Step 5: Verify Installation
To check if LiteLLM is running correctly, list all pods in your specified namespace:
kubectl get pods -n <your-namespace>
You should see a pod named something like litellm-<random-suffix>
.
Step 6: Access LiteLLM
If you set the service type to LoadBalancer
, you can get the external IP address with:
kubectl get svc -n <your-namespace>
Access LiteLLM via http://<external-ip>:8000
.
Following the above steps you can install litellm using helm.